Making attention mechanisms more robust and interpretable with virtual adversarial training.
Shunsuke KitadaHitoshi IyatomiPublished in: Appl. Intell. (2023)
Keyphrases
- genetic algorithm
- neural network
- augmented reality
- training set
- virtual reality
- virtual world
- artificial intelligence
- information systems
- visual attention
- hidden markov models
- test set
- training samples
- mechanisms underlying
- parameter tuning
- training examples
- computationally efficient
- vision system
- optical flow
- object recognition
- image sequences
- learning algorithm